[next-queue v6 PATCH 0/7] i40e: Add port representor and initial switchdev support

@@ -215,6 +215,7 @@ config I40E
 	tristate "Intel(R) Ethernet Controller XL710 Family support"
 	imply PTP_1588_CLOCK
 	depends on PCI
+	depends on MAY_USE_DEVLINK
 	---help---
 	  This driver supports Intel(R) Ethernet Controller XL710 Family of
 	  devices.  For more information on how to identify your adapter, go

@@ -54,6 +54,8 @@
 #include <linux/clocksource.h>
 #include <linux/net_tstamp.h>
 #include <linux/ptp_clock_kernel.h>
+#include <net/devlink.h>
+
 #include "i40e_type.h"
 #include "i40e_prototype.h"
 #include "i40e_client.h"

@@ -517,6 +519,7 @@ struct i40e_pf {
 	u32 ioremap_len;
 	u32 fd_inv;
 	u16 phy_led_val;
+	enum devlink_eswitch_mode eswitch_mode;
 };
 
 /**

@@ -10823,6 +10823,57 @@ static void i40e_get_platform_mac_addr(struct pci_dev *pdev, struct i40e_pf *pf)
 }
 
 /**
+ * i40e_devlink_eswitch_mode_get
+ *
+ * @devlink: pointer to devlink struct
+ * @mode: sr-iov switch mode pointer
+ *
+ * Returns the switch mode of the associated PF in the @mode pointer.
+ */
+static int i40e_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
+{
+	struct i40e_pf *pf = devlink_priv(devlink);
+
+	*mode = pf->eswitch_mode;
+
+	return 0;
+}
+
+/**
+ * i40e_devlink_eswitch_mode_set
+ *
+ * @devlink: pointer to devlink struct
+ * @mode: sr-iov switch mode
+ *
+ * Set the switch mode of the associated PF.
+ * Returns 0 on success and -EOPNOTSUPP on error.
+ */
+static int i40e_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode)
+{
+	struct i40e_pf *pf = devlink_priv(devlink);
+	int err = 0;
+
+	if (mode == pf->eswitch_mode)
+		goto done;
+
+	switch (mode) {
+	case DEVLINK_ESWITCH_MODE_LEGACY:
+		pf->eswitch_mode = mode;
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+done:
+	return err;
+}
+
+static const struct devlink_ops i40e_devlink_ops = {
+	.eswitch_mode_get = i40e_devlink_eswitch_mode_get,
+	.eswitch_mode_set = i40e_devlink_eswitch_mode_set,
+};
+
+/**
  * i40e_probe - Device initialization routine
  * @pdev: PCI device information struct
  * @ent: entry in i40e_pci_tbl

@@ -10839,6 +10890,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct i40e_pf *pf;
 	struct i40e_hw *hw;
 	static u16 pfs_found;
+	struct devlink *devlink;
 	u16 wol_nvm_bits;
 	u16 link_status;
 	int err, globr_probe = 1;

@@ -10877,11 +10929,15 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	 * the Admin Queue structures and then querying for the
 	 * device's current profile information.
 	 */
-	pf = kzalloc(sizeof(*pf), GFP_KERNEL);
-	if (!pf) {
+
+	devlink = devlink_alloc(&i40e_devlink_ops, sizeof(*pf));
+	if (!devlink) {
+		dev_err(&pdev->dev, "devlink_alloc failed\n");
 		err = -ENOMEM;
-		goto err_pf_alloc;
+		goto err_devlink_alloc;
 	}
+
+	pf = devlink_priv(devlink);
 	pf->next_vsi = 0;
 	pf->pdev = pdev;
 	set_bit(__I40E_DOWN, &pf->state);

@@ -11080,6 +11136,11 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	device_set_wakeup_enable(&pf->pdev->dev, pf->wol_en);
 
 	/* set up the main switch operations */
+	pf->eswitch_mode = DEVLINK_ESWITCH_MODE_LEGACY;
+	err = devlink_register(devlink, &pdev->dev);
+	if (err)
+		goto err_devlink_register;
+
 	i40e_determine_queue_usage(pf);
 	err = i40e_init_interrupt_scheme(pf);
 	if (err)

@@ -11339,6 +11400,8 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 err_switch_setup:
 	i40e_reset_interrupt_capability(pf);
 	del_timer_sync(&pf->service_timer);
+	devlink_unregister(devlink);
+err_devlink_register:
 err_mac_addr:
 err_configure_lan_hmc:
 	(void)i40e_shutdown_lan_hmc(hw);

@@ -11349,8 +11412,8 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 err_pf_reset:
 	iounmap(hw->hw_addr);
 err_ioremap:
-	kfree(pf);
-err_pf_alloc:
+	devlink_free(devlink);
+err_devlink_alloc:
 	pci_disable_pcie_error_reporting(pdev);
 	pci_release_mem_regions(pdev);
 err_pci_reg:

@@ -11372,6 +11435,7 @@ static void i40e_remove(struct pci_dev *pdev)
 {
 	struct i40e_pf *pf = pci_get_drvdata(pdev);
 	struct i40e_hw *hw = &pf->hw;
+	struct devlink *devlink = priv_to_devlink(pf);
 	i40e_status ret_code;
 	int i;
 

@@ -11458,7 +11522,8 @@ static void i40e_remove(struct pci_dev *pdev)
 	kfree(pf->vsi);
 
 	iounmap(hw->hw_addr);
-	kfree(pf);
+	devlink_unregister(devlink);
+	devlink_free(devlink);
 	pci_release_mem_regions(pdev);
 
 	pci_disable_pcie_error_reporting(pdev);

@@ -320,6 +320,17 @@ struct i40e_flex_pit {
 	u8 pit_index;
 };
 
+enum i40e_port_netdev_type {
+	I40E_PORT_NETDEV_PF,
+	I40E_PORT_NETDEV_VF
+};
+
+/* Port representor netdev private structure */
+struct i40e_port_netdev_priv {
+	enum i40e_port_netdev_type type;	/* type - PF or VF */
+	void *f;				/* ptr to PF or VF struct */
+};
+
 /* struct that defines the Ethernet device */
 struct i40e_pf {
 	struct pci_dev *pdev;

@@ -328,6 +339,12 @@ struct i40e_pf {
 	struct msix_entry *msix_entries;
 	bool fc_autoneg_status;
 
+	/* PF Port representor netdev that allows control and configuration of
+	 * PFs when they are moved to a different namespace. Enables returning
+	 * PF stats, configuring/monitoring link state, fdb/vlans, filters etc.
+	 */
+	struct net_device *port_netdev;
+
 	u16 eeprom_version;
 	u16 num_vmdq_vsis;         /* num vmdq vsis this PF has set up */
 	u16 num_vmdq_qps;          /* num queue pairs per vmdq pool */

@@ -985,4 +1002,6 @@ bool i40e_dcb_need_reconfig(struct i40e_pf *pf,
 i40e_status i40e_set_npar_bw_setting(struct i40e_pf *pf);
 i40e_status i40e_commit_npar_bw_setting(struct i40e_pf *pf);
 void i40e_print_link_message(struct i40e_vsi *vsi, bool isup);
+int i40e_alloc_port_netdev(void *f, enum i40e_port_netdev_type type);
+void i40e_free_port_netdev(void *f, enum i40e_port_netdev_type type);
 #endif /* _I40E_H_ */

@@ -9985,6 +9985,11 @@ struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type,
 					 ret);
 			}
 		}
+		if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) {
+			ret = i40e_alloc_port_netdev(pf, I40E_PORT_NETDEV_PF);
+			if (ret)
+				goto err_port_netdev;
+		}
 	case I40E_VSI_VMDQ2:
 		ret = i40e_config_netdev(vsi);
 		if (ret)

@@ -10037,6 +10042,9 @@ struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type,
 		vsi->netdev = NULL;
 	}
 err_netdev:
+	if (pf->port_netdev)
+		i40e_free_port_netdev(pf, I40E_PORT_NETDEV_PF);
+err_port_netdev:
 	i40e_aq_delete_element(&pf->hw, vsi->seid, NULL);
 err_vsi:
 	i40e_vsi_clear(vsi);

@@ -10851,13 +10859,38 @@ static int i40e_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
 static int i40e_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode)
 {
 	struct i40e_pf *pf = devlink_priv(devlink);
-	int err = 0;
+	struct i40e_vf *vf;
+	int i, j, err = 0;
 
 	if (mode == pf->eswitch_mode)
 		goto done;
 
 	switch (mode) {
 	case DEVLINK_ESWITCH_MODE_LEGACY:
+		for (i = 0; i < pf->num_alloc_vfs; i++) {
+			vf = &pf->vf[i];
+			i40e_free_port_netdev(vf, I40E_PORT_NETDEV_VF);
+		}
+		i40e_free_port_netdev(pf, I40E_PORT_NETDEV_PF);
+		pf->eswitch_mode = mode;
+		break;
+	case DEVLINK_ESWITCH_MODE_SWITCHDEV:
+		err = i40e_alloc_port_netdev(pf, I40E_PORT_NETDEV_PF);
+		if (err)
+			goto done;
+		for (i = 0; i < pf->num_alloc_vfs; i++) {
+			vf = &pf->vf[i];
+			err = i40e_alloc_port_netdev(vf, I40E_PORT_NETDEV_VF);
+			if (err) {
+				for (j = 0; j < i; j++) {
+					vf = &pf->vf[j];
+					i40e_free_port_netdev(vf,
+							I40E_PORT_NETDEV_VF);
+				}
+				i40e_free_port_netdev(pf, I40E_PORT_NETDEV_PF);
+				goto done;
+			}
+		}
 		pf->eswitch_mode = mode;
 		break;
 	default:

@@ -10874,6 +10907,157 @@ static int i40e_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode)
 };
 
 /**
+ * i40e_port_netdev_open
+ * @dev: network interface device structure
+ *
+ * Called when port netdevice is brought up.
+ **/
+static int i40e_port_netdev_open(struct net_device *dev)
+{
+	return 0;
+}
+
+/**
+ * i40e_port_netdev_stop
+ * @dev: network interface device structure
+ *
+ * Called when port netdevice is brought down.
+ **/
+static int i40e_port_netdev_stop(struct net_device *dev)
+{
+	return 0;
+}
+
+static const struct net_device_ops i40e_port_netdev_ops = {
+	.ndo_open		= i40e_port_netdev_open,
+	.ndo_stop		= i40e_port_netdev_stop,
+};
+
+/**
+ * i40e_alloc_port_netdev
+ * @f: pointer to the PF or VF structure
+ * @type: port netdev type
+ *
+ * Create Port representor netdev
+ **/
+int i40e_alloc_port_netdev(void *f, enum i40e_port_netdev_type type)
+{
+	struct net_device *port_netdev;
+	char netdev_name[IFNAMSIZ];
+	struct i40e_port_netdev_priv *priv;
+	struct i40e_pf *pf;
+	struct i40e_vf *vf;
+	struct i40e_vsi *vsi;
+	int err;
+
+	switch (type) {
+	case I40E_PORT_NETDEV_PF:
+		pf = (struct i40e_pf *)f;
+		vsi = pf->vsi[pf->lan_vsi];
+
+		snprintf(netdev_name, IFNAMSIZ, "%s-pf", vsi->netdev->name);
+		port_netdev = alloc_netdev(sizeof(struct i40e_port_netdev_priv),
+					   netdev_name, NET_NAME_UNKNOWN,
+					   ether_setup);
+		if (!port_netdev) {
+			dev_err(&pf->pdev->dev,
+				"alloc_netdev failed for PF:%s port netdev\n",
+				vsi->netdev->name);
+			return -ENOMEM;
+		}
+		pf->port_netdev = port_netdev;
+		priv = netdev_priv(port_netdev);
+		priv->f = pf;
+		priv->type = I40E_PORT_NETDEV_PF;
+		break;
+	case I40E_PORT_NETDEV_VF:
+		vf = (struct i40e_vf *)f;
+		pf = vf->pf;
+		vsi = pf->vsi[pf->lan_vsi];
+
+		snprintf(netdev_name, IFNAMSIZ, "%s-vf%d", vsi->netdev->name,
+			 vf->vf_id);
+		port_netdev = alloc_netdev(sizeof(struct i40e_port_netdev_priv),
+					   netdev_name, NET_NAME_UNKNOWN,
+					   ether_setup);
+		if (!port_netdev) {
+			dev_err(&pf->pdev->dev,
+				"alloc_netdev failed for VF%d port netdev\n",
+				vf->vf_id);
+			return -ENOMEM;
+		}
+		vf->port_netdev = port_netdev;
+		priv = netdev_priv(port_netdev);
+		priv->f = vf;
+		priv->type = I40E_PORT_NETDEV_VF;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	port_netdev->netdev_ops = &i40e_port_netdev_ops;
+	eth_hw_addr_random(port_netdev);
+
+	netif_carrier_off(port_netdev);
+	netif_tx_stop_all_queues(port_netdev);
+
+	err = register_netdev(port_netdev);
+	if (err) {
+		dev_err(&pf->pdev->dev, "register_netdev failed for port netdev: %s\n",
+			port_netdev->name);
+		free_netdev(port_netdev);
+		return err;
+	}
+
+	dev_info(&pf->pdev->dev, "%s Port representor %s created\n",
+		 ((type == I40E_PORT_NETDEV_PF) ? "PF" : "VF"),
+		 port_netdev->name);
+
+	return 0;
+}
+
+/**
+ * i40e_free_port_netdev
+ * @pf: pointer to the PF or VF structure
+ * @type: port netdev type
+ *
+ * Free Port representor netdev
+ **/
+void i40e_free_port_netdev(void *f, enum i40e_port_netdev_type type)
+{
+	struct i40e_pf *pf;
+	struct i40e_vf *vf;
+
+	switch (type) {
+	case I40E_PORT_NETDEV_PF:
+		pf = (struct i40e_pf *)f;
+
+		if (!pf->port_netdev)
+			return;
+		dev_info(&pf->pdev->dev, "Freeing PF Port representor %s\n",
+			 pf->port_netdev->name);
+		unregister_netdev(pf->port_netdev);
+		free_netdev(pf->port_netdev);
+		pf->port_netdev = NULL;
+		break;
+	case I40E_PORT_NETDEV_VF:
+		vf = (struct i40e_vf *)f;
+		pf = vf->pf;
+
+		if (!vf->port_netdev)
+			return;
+		dev_info(&pf->pdev->dev, "Freeing VF Port representor %s\n",
+			 vf->port_netdev->name);
+		unregister_netdev(vf->port_netdev);
+		free_netdev(vf->port_netdev);
+		vf->port_netdev = NULL;
+		break;
+	default:
+		break;
+	}
+}
+
+/**
  * i40e_probe - Device initialization routine
  * @pdev: PCI device information struct
  * @ent: entry in i40e_pci_tbl

@@ -11474,6 +11658,7 @@ static void i40e_remove(struct pci_dev *pdev)
 			i40e_switch_branch_release(pf->veb[i]);
 	}
 
+	i40e_free_port_netdev(pf, I40E_PORT_NETDEV_PF);
 	/* Now we can shutdown the PF's VSI, just before we kill
 	 * adminq and hmc.
 	 */

@@ -1081,6 +1081,9 @@ void i40e_free_vfs(struct i40e_pf *pf)
 			i40e_free_vf_res(&pf->vf[i]);
 		/* disable qp mappings */
 		i40e_disable_vf_mappings(&pf->vf[i]);
+
+		if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_SWITCHDEV)
+			i40e_free_port_netdev(&pf->vf[i], I40E_PORT_NETDEV_VF);
 	}
 
 	kfree(pf->vf);

@@ -1148,6 +1151,12 @@ int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs)
 		/* VF resources get allocated during reset */
 		i40e_reset_vf(&vfs[i], false);
 
+		if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) {
+			ret = i40e_alloc_port_netdev(&vfs[i],
+						     I40E_PORT_NETDEV_VF);
+			if (ret)
+				goto err_alloc;
+		}
 	}
 	pf->num_alloc_vfs = num_alloc_vfs;
 

@@ -76,6 +76,12 @@ enum i40e_vf_capabilities {
 struct i40e_vf {
 	struct i40e_pf *pf;
 
+	/* VF Port representor netdev that allows control and configuration
+	 * of VFs from the host. Enables returning VF stats, configuring link
+	 * state, mtu, fdb/vlans, filters etc.
+	 */
+	struct net_device *port_netdev;
+
 	/* VF id in the PF space */
 	s16 vf_id;
 	/* all VF vsis connect to the same parent */

@@ -5,10 +5,22 @@
 #include <net/ip_tunnels.h>
 #include <net/dst.h>
 
+enum metadata_type {
+	METADATA_IP_TUNNEL,
+	METADATA_HW_PORT_MUX,
+};
+
+struct hw_port_info {
+	struct net_device *lower_dev;
+	u32 port_id;
+};
+
 struct metadata_dst {
 	struct dst_entry		dst;
+	enum metadata_type		type;
 	union {
 		struct ip_tunnel_info	tun_info;
+		struct hw_port_info	port_info;
 	} u;
 };
 

@@ -27,7 +39,7 @@ static inline struct ip_tunnel_info *skb_tunnel_info(struct sk_buff *skb)
 	struct metadata_dst *md_dst = skb_metadata_dst(skb);
 	struct dst_entry *dst;
 
-	if (md_dst)
+	if (md_dst && md_dst->type == METADATA_IP_TUNNEL)
 		return &md_dst->u.tun_info;
 
 	dst = skb_dst(skb);

@@ -55,22 +67,33 @@ static inline int skb_metadata_dst_cmp(const struct sk_buff *skb_a,
 	a = (const struct metadata_dst *) skb_dst(skb_a);
 	b = (const struct metadata_dst *) skb_dst(skb_b);
 
-	if (!a != !b || a->u.tun_info.options_len != b->u.tun_info.options_len)
+	if (!a != !b || a->type != b->type)
 		return 1;
 
-	return memcmp(&a->u.tun_info, &b->u.tun_info,
-		      sizeof(a->u.tun_info) + a->u.tun_info.options_len);
+	switch (a->type) {
+	case METADATA_HW_PORT_MUX:
+		return memcmp(&a->u.port_info, &b->u.port_info,
+			      sizeof(a->u.port_info));
+	case METADATA_IP_TUNNEL:
+		return memcmp(&a->u.tun_info, &b->u.tun_info,
+			      sizeof(a->u.tun_info) +
+					 a->u.tun_info.options_len);
+	default:
+		return 1;
+	}
 }
 
 void metadata_dst_free(struct metadata_dst *);
-struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags);
-struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags);
+struct metadata_dst *metadata_dst_alloc(u8 optslen, enum metadata_type type,
+					gfp_t flags);
+struct metadata_dst __percpu *
+metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags);
 
 static inline struct metadata_dst *tun_rx_dst(int md_size)
 {
 	struct metadata_dst *tun_dst;
 
-	tun_dst = metadata_dst_alloc(md_size, GFP_ATOMIC);
+	tun_dst = metadata_dst_alloc(md_size, METADATA_IP_TUNNEL, GFP_ATOMIC);
 	if (!tun_dst)
 		return NULL;
 

@@ -85,11 +108,11 @@ static inline struct metadata_dst *tun_dst_unclone(struct sk_buff *skb)
 	int md_size;
 	struct metadata_dst *new_md;
 
-	if (!md_dst)
+	if (!md_dst || md_dst->type != METADATA_IP_TUNNEL)
 		return ERR_PTR(-EINVAL);
 
 	md_size = md_dst->u.tun_info.options_len;
-	new_md = metadata_dst_alloc(md_size, GFP_ATOMIC);
+	new_md = metadata_dst_alloc(md_size, METADATA_IP_TUNNEL, GFP_ATOMIC);
 	if (!new_md)
 		return ERR_PTR(-ENOMEM);
 

@@ -366,7 +366,9 @@ static int dst_md_discard(struct sk_buff *skb)
 	return 0;
 }
 
-static void __metadata_dst_init(struct metadata_dst *md_dst, u8 optslen)
+static void __metadata_dst_init(struct metadata_dst *md_dst,
+				enum metadata_type type, u8 optslen)
+
 {
 	struct dst_entry *dst;
 

@@ -378,9 +380,11 @@ static void __metadata_dst_init(struct metadata_dst *md_dst, u8 optslen)
 	dst->output = dst_md_discard_out;
 
 	memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst));
+	md_dst->type = type;
 }
 
-struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags)
+struct metadata_dst *metadata_dst_alloc(u8 optslen, enum metadata_type type,
+					gfp_t flags)
 {
 	struct metadata_dst *md_dst;
 

@@ -388,7 +392,7 @@ struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags)
 	if (!md_dst)
 		return NULL;
 
-	__metadata_dst_init(md_dst, optslen);
+	__metadata_dst_init(md_dst, type, optslen);
 
 	return md_dst;
 }

@@ -402,7 +406,8 @@ void metadata_dst_free(struct metadata_dst *md_dst)
 	kfree(md_dst);
 }
 
-struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags)
+struct metadata_dst __percpu *
+metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags)
 {
 	int cpu;
 	struct metadata_dst __percpu *md_dst;

@@ -413,7 +418,7 @@ struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags)
 		return NULL;
 
 	for_each_possible_cpu(cpu)
-		__metadata_dst_init(per_cpu_ptr(md_dst, cpu), optslen);
+		__metadata_dst_init(per_cpu_ptr(md_dst, cpu), type, optslen);
 
 	return md_dst;
 }

@@ -2531,6 +2531,7 @@ static unsigned short bpf_tunnel_key_af(u64 flags)
 		 * that is holding verifier mutex.
 		 */
 		md_dst = metadata_dst_alloc_percpu(IP_TUNNEL_OPTS_MAX,
+						   METADATA_IP_TUNNEL,
 						   GFP_KERNEL);
 		if (!md_dst)
 			return NULL;

@@ -134,10 +134,12 @@ struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md,
 	struct metadata_dst *res;
 	struct ip_tunnel_info *dst, *src;
 
-	if (!md || md->u.tun_info.mode & IP_TUNNEL_INFO_TX)
+	if (!md || md->type != METADATA_IP_TUNNEL ||
+	    md->u.tun_info.mode & IP_TUNNEL_INFO_TX)
+
 		return NULL;
 
-	res = metadata_dst_alloc(0, flags);
+	res = metadata_dst_alloc(0, METADATA_IP_TUNNEL, flags);
 	if (!res)
 		return NULL;
 

@@ -2202,7 +2202,9 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
 	if (start < 0)
 		return start;
 
-	tun_dst = metadata_dst_alloc(key.tun_opts_len, GFP_KERNEL);
+	tun_dst = metadata_dst_alloc(key.tun_opts_len, METADATA_IP_TUNNEL,
+				     GFP_KERNEL);
+
 	if (!tun_dst)
 		return -ENOMEM;
 

@@ -5316,7 +5316,8 @@ static int i40e_up_complete(struct i40e_vsi *vsi)
 	i40e_vsi_enable_irq(vsi);
 
 	if ((pf->hw.phy.link_info.link_info & I40E_AQ_LINK_UP) &&
-	    (vsi->netdev)) {
+	    (vsi->netdev) && (!pf->port_netdev ||
+			      (pf->port_netdev->flags & IFF_UP))) {
 		i40e_print_link_message(vsi, true);
 		netif_tx_start_all_queues(vsi->netdev);
 		netif_carrier_on(vsi->netdev);

@@ -5518,6 +5519,9 @@ int i40e_open(struct net_device *netdev)
 
 	udp_tunnel_get_rx_info(netdev);
 
+	if (pf->port_netdev)
+		netif_carrier_on(pf->port_netdev);
+
 	return 0;
 }
 

@@ -5667,9 +5671,13 @@ int i40e_close(struct net_device *netdev)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
+	struct i40e_pf *pf = vsi->back;
 
 	i40e_vsi_close(vsi);
 
+	if (pf->port_netdev)
+		netif_carrier_off(pf->port_netdev);
+
 	return 0;
 }
 

@@ -6181,10 +6189,15 @@ static void i40e_vsi_link_event(struct i40e_vsi *vsi, bool link_up)
 
 	switch (vsi->type) {
 	case I40E_VSI_MAIN:
+	{
+		struct i40e_pf *pf = vsi->back;
+		struct net_device *port_netdev = pf->port_netdev;
+
 		if (!vsi->netdev || !vsi->netdev_registered)
 			break;
 
-		if (link_up) {
+		if (link_up && (!port_netdev ||
+				(port_netdev->flags & IFF_UP))) {
 			netif_carrier_on(vsi->netdev);
 			netif_tx_wake_all_queues(vsi->netdev);
 		} else {

@@ -6192,7 +6205,7 @@ static void i40e_vsi_link_event(struct i40e_vsi *vsi, bool link_up)
 			netif_tx_stop_all_queues(vsi->netdev);
 		}
 		break;
-
+	}
 	case I40E_VSI_SRIOV:
 	case I40E_VSI_VMDQ2:
 	case I40E_VSI_CTRL:

@@ -10914,7 +10927,35 @@ static int i40e_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode)
  **/
 static int i40e_port_netdev_open(struct net_device *dev)
 {
-	return 0;
+	struct i40e_port_netdev_priv *priv = netdev_priv(dev);
+	struct i40e_pf *pf;
+	struct i40e_vf *vf;
+	struct i40e_vsi *vsi;
+	int err = 0;
+
+	switch (priv->type) {
+	case I40E_PORT_NETDEV_VF:
+		vf = (struct i40e_vf *)priv->f;
+		vf->link_forced = true;
+		vf->link_up = true;
+		i40e_vc_notify_vf_link_state(vf);
+		break;
+	case I40E_PORT_NETDEV_PF:
+		pf = (struct i40e_pf *)priv->f;
+		vsi = pf->vsi[pf->lan_vsi];
+		if (pf->hw.phy.link_info.link_info & I40E_AQ_LINK_UP) {
+			netif_carrier_on(vsi->netdev);
+			netif_tx_start_all_queues(vsi->netdev);
+		} else {
+			err = -ENETDOWN;
+		}
+		break;
+	default:
+		err = -EINVAL;
+		break;
+	}
+
+	return err;
 }
 
 /**

@@ -10925,7 +10966,31 @@ static int i40e_port_netdev_open(struct net_device *dev)
  **/
 static int i40e_port_netdev_stop(struct net_device *dev)
 {
-	return 0;
+	struct i40e_port_netdev_priv *priv = netdev_priv(dev);
+	struct i40e_pf *pf;
+	struct i40e_vf *vf;
+	struct i40e_vsi *vsi;
+	int err = 0;
+
+	switch (priv->type) {
+	case I40E_PORT_NETDEV_VF:
+		vf = (struct i40e_vf *)priv->f;
+		vf->link_forced = true;
+		vf->link_up = false;
+		i40e_vc_notify_vf_link_state(vf);
+		break;
+	case I40E_PORT_NETDEV_PF:
+		pf = (struct i40e_pf *)priv->f;
+		vsi = pf->vsi[pf->lan_vsi];
+		netif_carrier_off(vsi->netdev);
+		netif_tx_stop_all_queues(vsi->netdev);
+		break;
+	default:
+		err = -EINVAL;
+		break;
+	}
+
+	return err;
 }
 
 static const struct net_device_ops i40e_port_netdev_ops = {

@@ -11013,6 +11078,26 @@ int i40e_alloc_port_netdev(void *f, enum i40e_port_netdev_type type)
 		 ((type == I40E_PORT_NETDEV_PF) ? "PF" : "VF"),
 		 port_netdev->name);
 
+	switch (type) {
+	case I40E_PORT_NETDEV_PF:
+		/* Reset PF link as we are changing the mode to 'switchdev'.
+		 * Port netdev needs to be brought up to enable VF link.
+		 */
+		netif_carrier_off(vsi->netdev);
+		netif_tx_stop_all_queues(vsi->netdev);
+		if (pf->hw.phy.link_info.link_info & I40E_AQ_LINK_UP)
+			netif_carrier_on(port_netdev);
+		break;
+	case I40E_PORT_NETDEV_VF:
+		/* Reset VF link as we are changing the mode to 'switchdev'.
+		 * Port netdev needs to be brought up to enable VF link.
+		 */
+		vf->link_forced = true;
+		vf->link_up = false;
+		i40e_vc_notify_vf_link_state(vf);
+		break;
+	}
+
 	return 0;
 }
 

@@ -11027,10 +11112,12 @@ void i40e_free_port_netdev(void *f, enum i40e_port_netdev_type type)
 {
 	struct i40e_pf *pf;
 	struct i40e_vf *vf;
+	struct i40e_vsi *vsi;
 
 	switch (type) {
 	case I40E_PORT_NETDEV_PF:
 		pf = (struct i40e_pf *)f;
+		vsi = pf->vsi[pf->lan_vsi];
 
 		if (!pf->port_netdev)
 			return;

@@ -11039,6 +11126,11 @@ void i40e_free_port_netdev(void *f, enum i40e_port_netdev_type type)
 		unregister_netdev(pf->port_netdev);
 		free_netdev(pf->port_netdev);
 		pf->port_netdev = NULL;
+		/* In legacy mode, PF link is not controlled by Port netdev */
+		if (pf->hw.phy.link_info.link_info & I40E_AQ_LINK_UP) {
+			netif_carrier_on(vsi->netdev);
+			netif_tx_start_all_queues(vsi->netdev);
+		}
 		break;
 	case I40E_PORT_NETDEV_VF:
 		vf = (struct i40e_vf *)f;

@@ -11051,6 +11143,10 @@ void i40e_free_port_netdev(void *f, enum i40e_port_netdev_type type)
 		unregister_netdev(vf->port_netdev);
 		free_netdev(vf->port_netdev);
 		vf->port_netdev = NULL;
+
+		/* In legacy mode, VF link is not controlled by Port netdev */
+		vf->link_forced = false;
+		i40e_vc_notify_vf_link_state(vf);
 		break;
 	default:
 		break;

@@ -68,7 +68,7 @@ static void i40e_vc_vf_broadcast(struct i40e_pf *pf,
  *
  * send a link status message to a single VF
  **/
-static void i40e_vc_notify_vf_link_state(struct i40e_vf *vf)
+void i40e_vc_notify_vf_link_state(struct i40e_vf *vf)
 {
 	struct i40e_virtchnl_pf_event pfe;
 	struct i40e_pf *pf = vf->pf;

@@ -1805,6 +1805,10 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 
 	if (i40e_vsi_start_rings(pf->vsi[vf->lan_vsi_idx]))
 		aq_ret = I40E_ERR_TIMEOUT;
+
+	if ((aq_ret == 0) && vf->port_netdev)
+		netif_carrier_on(vf->port_netdev);
+
 error_param:
 	/* send the response to the VF */
 	return i40e_vc_send_resp_to_vf(vf, I40E_VIRTCHNL_OP_ENABLE_QUEUES,

@@ -1844,6 +1848,9 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 
 	i40e_vsi_stop_rings(pf->vsi[vf->lan_vsi_idx]);
 
+	if ((aq_ret == 0) && vf->port_netdev)
+		netif_carrier_off(vf->port_netdev);
+
 error_param:
 	/* send the response to the VF */
 	return i40e_vc_send_resp_to_vf(vf, I40E_VIRTCHNL_OP_DISABLE_QUEUES,

@@ -3080,6 +3087,7 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link)
 	struct i40e_pf *pf = np->vsi->back;
 	struct i40e_virtchnl_pf_event pfe;
 	struct i40e_hw *hw = &pf->hw;
+	struct net_device *port_netdev;
 	struct i40e_vf *vf;
 	int abs_vf_id;
 	int ret = 0;

@@ -3121,6 +3129,17 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link)
 		ret = -EINVAL;
 		goto error_out;
 	}
+
+	port_netdev = vf->port_netdev;
+	if (port_netdev) {
+		unsigned int flags = port_netdev->flags;
+
+		if (vf->link_up)
+			dev_change_flags(port_netdev, flags | IFF_UP);
+		else
+			dev_change_flags(port_netdev, flags & ~IFF_UP);
+	}
+
 	/* Notify the VF of its new link state */
 	i40e_aq_send_msg_to_vf(hw, abs_vf_id, I40E_VIRTCHNL_OP_EVENT,
 			       0, (u8 *)&pfe, sizeof(pfe), NULL);

@@ -146,5 +146,6 @@ int i40e_ndo_get_vf_config(struct net_device *netdev,
 
 void i40e_vc_notify_link_state(struct i40e_pf *pf);
 void i40e_vc_notify_reset(struct i40e_pf *pf);
+void i40e_vc_notify_vf_link_state(struct i40e_vf *vf);
 
 #endif /* _I40E_VIRTCHNL_PF_H_ */

@@ -55,6 +55,7 @@
 #include <linux/net_tstamp.h>
 #include <linux/ptp_clock_kernel.h>
 #include <net/devlink.h>
+#include <net/dst_metadata.h>
 
 #include "i40e_type.h"
 #include "i40e_prototype.h"

@@ -320,6 +321,8 @@ struct i40e_flex_pit {
 	u8 pit_index;
 };
 
+#define I40E_MAIN_VSI_PORT_ID	(1 << 15)
+
 enum i40e_port_netdev_type {
 	I40E_PORT_NETDEV_PF,
 	I40E_PORT_NETDEV_VF

@@ -328,6 +331,7 @@ enum i40e_port_netdev_type {
 /* Port representor netdev private structure */
 struct i40e_port_netdev_priv {
 	enum i40e_port_netdev_type type;	/* type - PF or VF */
+	struct metadata_dst *dst;		/* port id */
 	void *f;				/* ptr to PF or VF struct */
 };
 

@@ -5519,8 +5519,10 @@ int i40e_open(struct net_device *netdev)
 
 	udp_tunnel_get_rx_info(netdev);
 
-	if (pf->port_netdev)
+	if (pf->port_netdev) {
 		netif_carrier_on(pf->port_netdev);
+		netif_tx_start_all_queues(pf->port_netdev);
+	}
 
 	return 0;
 }

@@ -5675,8 +5677,10 @@ int i40e_close(struct net_device *netdev)
 
 	i40e_vsi_close(vsi);
 
-	if (pf->port_netdev)
+	if (pf->port_netdev) {
 		netif_carrier_off(pf->port_netdev);
+		netif_tx_stop_all_queues(pf->port_netdev);
+	}
 
 	return 0;
 }

@@ -10872,6 +10876,7 @@ static int i40e_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
 static int i40e_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode)
 {
 	struct i40e_pf *pf = devlink_priv(devlink);
+	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
 	struct i40e_vf *vf;
 	int i, j, err = 0;
 

@@ -10886,6 +10891,8 @@ static int i40e_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode)
 		}
 		i40e_free_port_netdev(pf, I40E_PORT_NETDEV_PF);
 		pf->eswitch_mode = mode;
+		vsi->netdev->priv_flags |=
+			(IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM);
 		break;
 	case DEVLINK_ESWITCH_MODE_SWITCHDEV:
 		err = i40e_alloc_port_netdev(pf, I40E_PORT_NETDEV_PF);

@@ -10905,6 +10912,7 @@ static int i40e_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode)
 			}
 		}
 		pf->eswitch_mode = mode;
+		netif_keep_dst(vsi->netdev);
 		break;
 	default:
 		err = -EOPNOTSUPP;

@@ -10996,6 +11004,7 @@ static int i40e_port_netdev_stop(struct net_device *dev)
 static const struct net_device_ops i40e_port_netdev_ops = {
 	.ndo_open		= i40e_port_netdev_open,
 	.ndo_stop		= i40e_port_netdev_stop,
+	.ndo_start_xmit		= i40e_port_netdev_start_xmit,
 };
 
 /**

@@ -11034,6 +11043,10 @@ int i40e_alloc_port_netdev(void *f, enum i40e_port_netdev_type type)
 		priv = netdev_priv(port_netdev);
 		priv->f = pf;
 		priv->type = I40E_PORT_NETDEV_PF;
+		priv->dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX,
+					       GFP_KERNEL);
+		priv->dst->u.port_info.lower_dev = vsi->netdev;
+		priv->dst->u.port_info.port_id = I40E_MAIN_VSI_PORT_ID;
 		break;
 	case I40E_PORT_NETDEV_VF:
 		vf = (struct i40e_vf *)f;

@@ -11055,6 +11068,10 @@ int i40e_alloc_port_netdev(void *f, enum i40e_port_netdev_type type)
 		priv = netdev_priv(port_netdev);
 		priv->f = vf;
 		priv->type = I40E_PORT_NETDEV_VF;
+		priv->dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX,
+					       GFP_KERNEL);
+		priv->dst->u.port_info.lower_dev = vsi->netdev;
+		priv->dst->u.port_info.port_id = vf->vf_id;
 		break;
 	default:
 		return -EINVAL;

@@ -11070,6 +11087,7 @@ int i40e_alloc_port_netdev(void *f, enum i40e_port_netdev_type type)
 	if (err) {
 		dev_err(&pf->pdev->dev, "register_netdev failed for port netdev: %s\n",
 			port_netdev->name);
+		dst_release((struct dst_entry *)priv->dst);
 		free_netdev(port_netdev);
 		return err;
 	}

@@ -11110,6 +11128,7 @@ int i40e_alloc_port_netdev(void *f, enum i40e_port_netdev_type type)
  **/
 void i40e_free_port_netdev(void *f, enum i40e_port_netdev_type type)
 {
+	struct i40e_port_netdev_priv *priv;
 	struct i40e_pf *pf;
 	struct i40e_vf *vf;
 	struct i40e_vsi *vsi;

@@ -11123,6 +11142,8 @@ void i40e_free_port_netdev(void *f, enum i40e_port_netdev_type type)
 			return;
 		dev_info(&pf->pdev->dev, "Freeing PF Port representor %s\n",
 			 pf->port_netdev->name);
+		priv = netdev_priv(pf->port_netdev);
+		dst_release((struct dst_entry *)priv->dst);
 		unregister_netdev(pf->port_netdev);
 		free_netdev(pf->port_netdev);
 		pf->port_netdev = NULL;